STATS 32: Introduction to R for Undergraduates
Elena Tuzhilina
Sep 28, 2021
http://web.stanford.edu/~elenatuz/courses/stats32-aut2021/
Recap of week 1
- Basics of R
- Data structures
- Homoegeneous: vectors & matrices
- Hetergeneous: list & data frames
- Packages
Vectors
vec <- c("a", "b", "c")
vec
## [1] "a" "b" "c"
## [1] "b" NA
Lists
classes <- list(quarter = "Fall 2018/19",
ID = c("STATS 32", "STATS 101", "STATS 200"),
credits = 12)
classes$ID
## [1] "STATS 32" "STATS 101" "STATS 200"
## [1] 12
Data frames
A special type of list:
- list keys are variable names of the dataset
- list values are all vectors of the same length (no. of observations)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
Getting a feel for your data
str, summaryhead, tailnames, dim, nrow, ncoltablemean, median, sd, varfactor
Agenda for today
- Different kinds of plots
- Plotting with
ggplot2 (and the + syntax)
Words vs. pictures
“The simple graph has brought more information to the data analyst’s mind than any other device.” - John Tukey
## mpg weight cylinders
## Mazda RX4 21.0 2.620 6
## Mazda RX4 Wag 21.0 2.875 6
## Datsun 710 22.8 2.320 4
## Hornet 4 Drive 21.4 3.215 6
## Hornet Sportabout 18.7 3.440 8
## Valiant 18.1 3.460 6
## Duster 360 14.3 3.570 8
## Merc 240D 24.4 3.190 4
## Merc 230 22.8 3.150 4
## Merc 280 19.2 3.440 6
## Merc 280C 17.8 3.440 6
## Merc 450SE 16.4 4.070 8
## Merc 450SL 17.3 3.730 8
## Merc 450SLC 15.2 3.780 8
## Cadillac Fleetwood 10.4 5.250 8
## Lincoln Continental 10.4 5.424 8
## Chrysler Imperial 14.7 5.345 8
## Fiat 128 32.4 2.200 4
## Honda Civic 30.4 1.615 4
## Toyota Corolla 33.9 1.835 4
## Toyota Corona 21.5 2.465 4
## Dodge Challenger 15.5 3.520 8
## AMC Javelin 15.2 3.435 8
## Camaro Z28 13.3 3.840 8
## Pontiac Firebird 19.2 3.845 8
## Fiat X1-9 27.3 1.935 4
## Porsche 914-2 26.0 2.140 4
## Lotus Europa 30.4 1.513 4
## Ford Pantera L 15.8 3.170 8
## Ferrari Dino 19.7 2.770 6
## Maserati Bora 15.0 3.570 8
## Volvo 142E 21.4 2.780 4
Words vs. pictures
“The simple graph has brought more information to the data analyst’s mind than any other device.” - John Tukey
## mpg weight cylinders
## Mazda RX4 21.0 2.620 6
## Mazda RX4 Wag 21.0 2.875 6
## Datsun 710 22.8 2.320 4
## Hornet 4 Drive 21.4 3.215 6
## Hornet Sportabout 18.7 3.440 8
## Valiant 18.1 3.460 6
## Duster 360 14.3 3.570 8
## Merc 240D 24.4 3.190 4
## Merc 230 22.8 3.150 4
## Merc 280 19.2 3.440 6
## Merc 280C 17.8 3.440 6
## Merc 450SE 16.4 4.070 8
## Merc 450SL 17.3 3.730 8
## Merc 450SLC 15.2 3.780 8
## Cadillac Fleetwood 10.4 5.250 8
## Lincoln Continental 10.4 5.424 8
## Chrysler Imperial 14.7 5.345 8
## Fiat 128 32.4 2.200 4
## Honda Civic 30.4 1.615 4
## Toyota Corolla 33.9 1.835 4
## Toyota Corona 21.5 2.465 4
## Dodge Challenger 15.5 3.520 8
## AMC Javelin 15.2 3.435 8
## Camaro Z28 13.3 3.840 8
## Pontiac Firebird 19.2 3.845 8
## Fiat X1-9 27.3 1.935 4
## Porsche 914-2 26.0 2.140 4
## Lotus Europa 30.4 1.513 4
## Ford Pantera L 15.8 3.170 8
## Ferrari Dino 19.7 2.770 6
## Maserati Bora 15.0 3.570 8
## Volvo 142E 21.4 2.780 4
Two classes of variables in statistics
- Continuous variable: Variable takes on values which fall on the real number line (or part of it)
- E.g. height, exam score, attendance count
- Categorical variable: Variable takes on values which fall into discrete categories
- E.g. ice-cream flavor, country of origin
Barplots: counts for a categorical variable
What is the distribution of cylinders in my dataset?
Histograms: counts for a continuous variable
What is the distribution of miles per gallon in my dataset?
Scatterplots: continuous variable vs. continuous variable
What is the relationship between mpg and weight?
Lineplots: continuous variable vs. time variable
What is the relationship between mpg and time?
Not so good… 
Easier to see the trend 
Boxplots & violin plots: continuous variable vs. categorical variable
For each value of cylinder, what is the distribution of mpg like?
Heatmaps: categorical variable vs. categorical variable
How often does each pair of cylinder and gear occur in the dataset?
Summary
- 1 categorical variable: barplot
- 1 continuous variable: histogram
- Continuous vs. continuous: scatterplot
- Continuous vs. time: lineplot
- Continuous vs. categorical: boxplots & violin plots
- Categorical vs. categorical: heatmap
Case study
I have father-son pairs. For each pair, I record their height and weight, as well as their ethnicities. I want to study the relationship between characteristics of the father and that of the son. What plots could help me?
Data visualization in R: 2 broad approaches
base R
ggplot2
How can we describe a graphic?
- The Grammar of Graphics, by Leland Wilkinson (1999)
- Motivating example: language
- Grammar: “a formal system of rules for generating lawful statements in a language”
- Can we develop similar rules for generating plots? Yes!
- Refined by Hadley Wickham’s “A Layered Grammar of Graphics” (2010)
Hadley Wickham
3 essential elements of graphics: data, geometries, aesthetics
Data: Dataset we are using for the plot
## mpg weight cylinders
## Mazda RX4 21.0 2.620 6
## Mazda RX4 Wag 21.0 2.875 6
## Datsun 710 22.8 2.320 4
## Hornet 4 Drive 21.4 3.215 6
## Hornet Sportabout 18.7 3.440 8
## Valiant 18.1 3.460 6
## Duster 360 14.3 3.570 8
## Merc 240D 24.4 3.190 4
## Merc 230 22.8 3.150 4
## Merc 280 19.2 3.440 6
3 essential elements of graphics: data, geometries, aesthetics
Geometries: Visual elements used for our data
- E.g. point, line, histogram, bar, boxplot
Geom: point
3 essential elements of graphics: data, geometries, aesthetics
Aesthetics: Defines the data columns which affect various aspects of the geom
- E.g. x, y, color, fill, size, alpha, line type, line width
- Which aesthetics you use depend on the geometries you choose
3 different aesthetics:
- x-axis: weight
- y-axis: mpg
- color: cylinders
- shape, size, etc. take on default values, not determined by data
Examples of other aesthetics
- x-axis: weight
- y-axis: mpg
- size: cylinders
- alpha: weight
Examples of other aesthetics
- x-axis: weight
- y-axis: mpg
- color: cylinders
- shape: cylinders
ggplot2 code
ggplot2 code
ggplot() +
geom_histogram(data = df, mapping = aes(x = mpg))
ggplot2 code
ggplot() +
geom_boxplot(data = df, mapping = aes(x = cylinders, y = mpg))
ggplot2 code
ggplot() +
geom_point(data = df,
mapping = aes(x = weight, y = mpg, col = cylinders),
shape = 15)
Today’s dataset: World Bank data
DataBank homepage
Interface for World Development Indicators
Full specification of a graphic
One graphic contains:
- 1 or more layers
- Each layer has 1 dataset, 1 geometric object, aesthetic mappings, 1 statistic (default usually ok), 1 position (default usually ok)
- 1 scale for each aesthetic mapping (defaults usually ok)
- 1 coordinate system (default usually ok)
- facet specification (if any)
Other grammatical elements: position
Sometimes we need to tweak the position of the geometric elements because they obscure each other.
- E.g. jitter: randomly shifting points slightly
Only 9 data points?? 
Much better 
Scales example: colors
Default colors
Manually chosen colors 
Shapes in R
Colors in R
- By name: e.g. “blue”, “red”, “black”, “white” (full list here)
- By RGB value: e.g.
rgb(0,0,1), rgb(1,0,0), rgb(0,0,0), rgb(1,1,1)
- By hexadecimal value: e.g “#0000FF”, “#FF0000”, “#000000”, “#FFFFFF”
